Automated Visual Content Analysis (AVCA) in Communication Research: A Protocol for Large Scale Image Classification with Pre-Trained Computer Vision Models

Araujo, Theo; Lock, Irina; Velde, Bob van de

doi:10.1080/19312458.2020.1810648

Cited by 25 publications

(10 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditionally, image and video analysis in communication research has relied on manual coding or qualitative methods, which tend to be more costly and less feasible because of the massive amount of visual data generated by the internet. In the past decade, powerful CV techniques, such as deep neural networks and pre-trained models, have gradually become more user friendly and have therefore become popular among social scientists (Araujo et al, 2020;Joo & Steinert-Threlkeld, 2018). Peng (2020) summarized four CV approaches for social scientists, and the present study uses two approaches: one leverages open-source or commercial CV artificial intelligence (AI) applications (e.g., Face++ and Microsoft Azure) to perform standardized tasks, such as facial recognition and emotion detection, and the other uses supervised learning convolutional neural network (CNN) models trained on a large number of labeled images to help classify images.…”

Section: Computer Vision Technologymentioning

confidence: 99%

Attraction behind “Beauty” Revealing Gay Men’s Self-Presentation on a Dating App with Computer Vision

Fan¹,

Chen²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

Profile photos, which are fundamental constructs of online self-presentation, are crucial to building successful online relationships. The visual cues embodied in profile photos are factors that help initiate socialization on visual-based gay dating platforms. This study applies app crawler techniques to collect publicly disclosed profile photos from Finka, a Chinese gay men’s dating app, and uses computer vision artificial intelligence applications to analyze the visual cues from the photos. The results show that appealing faces are relevant factors of user popularity, seemingly confirming the existence of the gay male beauty myth in the dating community. Photos that expose bodies are also popular, although most profile photos have low body visibility, which may be rooted in gay men’s culture in China. Extending existing research, we incorporate the background scene as another theoretical dimension of visual cues. Interestingly, we find an ambiance effect in profile photos—showing background scenes can serve as a self-presentation tactic that potentially influences users’ popularity. In particular, private scenes (e.g., locker room and bedroom scenes) can arouse more desire for further interaction with the presenter.

show abstract

Section: Computer Vision Technologymentioning

confidence: 99%

Attraction behind “Beauty” Revealing Gay Men’s Self-Presentation on a Dating App with Computer Vision

Fan¹,

Chen²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…For example, different services seem to provide substantially different labels for same images (Araujo et al, 2020; Ghermandi et al, 2022; Webb Williams et al, 2020). Figure 1 illustrates the inconsistencies between services.…”

Section: Introductionmentioning

confidence: 99%

Do you see what I see? Measuring the semantic differences in image‐recognition services' outputs

Berg,

Nelimarkka

2023

Asso for Info Science & Tech

View full text Add to dashboard Cite

As scholars increasingly undertake large‐scale analysis of visual materials, advanced computational tools show promise for informing that process. One technique in the toolbox is image recognition, made readily accessible via Google Vision AI, Microsoft Azure Computer Vision, and Amazon's Rekognition service. However, concerns about such issues as bias factors and low reliability have led to warnings against research employing it. A systematic study of cross‐service label agreement concretized such issues: using eight datasets, spanning professionally produced and user‐generated images, the work showed that image‐recognition services disagree on the most suitable labels for images. Beyond supporting caveats expressed in prior literature, the report articulates two mitigation strategies, both involving the use of multiple image‐recognition services: Highly explorative research could include all the labels, accepting noisier but less restrictive analysis output. Alternatively, scholars may employ word‐embedding‐based approaches to identify concepts that are similar enough for their purposes, then focus on those labels filtered in.

show abstract

“…For example, network science techniques have been developed and applied to the study of communication networks (Monge & Contractor, 2003) that were, in the past, out of reach (e.g., Jackson et al, 2020;Kenneth et al, 2020;Yang et al, 2020). Major efforts have also been invested in developing and validating techniques for automated text analysis (Guo et al, 2016;Maier et al, 2018;Scharkow, 2013;Van Atteveldt et al, 2021;Watanabe, 2021), and more recently, of computer vision (Araujo et al, 2020;Casas & Williams, 2020;Chen et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Worlds of Agents: Prospects of Agent-Based Modeling for Communication Research

Waldherr¹,

Hilbert

González‐Bailón

2021

Communication Methods and Measures

View full text Add to dashboard Cite

Agent-based computational models create virtual laboratories in which to formalize and simulate dynamic, multi-level theories of communication. They allow the systematic development of thought experiments, and they improve our understanding of the generative mechanisms that underlie patterns observed in empirical data. Simulation models help explore hypothetical and unprecedented scenarios, serving as powerful hypothesis generators for future theoretical and empirical research. This Special Issue showcases a collection of studies that demonstrate the analytical potential and methodological contribution of agent-based modeling (ABM) for media and communication research. In this introduction, we highlight five major benefits of this modeling approach to communication scholarship: (1) formalization, (2) understanding, (3) explanation, (4) prediction, and (5) exploration. We then present the four studies of this special issue, which contribute methodologically and theoretically to diverse key areas of communication: the emergence of meanings; political deliberation; information diffusion; and media use and social influence. We conclude with outlining future perspectives of ABM in communication research.

show abstract

Automated Visual Content Analysis (AVCA) in Communication Research: A Protocol for Large Scale Image Classification with Pre-Trained Computer Vision Models

Cited by 25 publications

References 84 publications

Attraction behind “Beauty” Revealing Gay Men’s Self-Presentation on a Dating App with Computer Vision

Attraction behind “Beauty” Revealing Gay Men’s Self-Presentation on a Dating App with Computer Vision

Do you see what I see? Measuring the semantic differences in image‐recognition services' outputs

Worlds of Agents: Prospects of Agent-Based Modeling for Communication Research

Contact Info

Product

Resources

About